提出了基于区域的多连接体(手指)的三维运动跟踪算法.该算法首先用多约束融合的方法以及手指的运动特性,得到初始帧手指的三维结构;然后根据刚性多连接体的运动模型以及相应的姿势约束模型,给出了这一特殊运动模型三维运动估计的优化算法,此算法能够鲁棒地估计手指的三维运动;最后利用区域跟踪的方法获取多连接体三维运动,并在真实的手指序列图象中实现了该算法.实验结果证实了该算法的有效性.

In this paper, a algorithm of region-based 3D motion tracking on multi-linkage is proposed. Firstly based on the fact that the length of fingers is same in motion, and each of them lies in the same virtual plane because of only one degree of freedom at their joints, which is defined as the rigidity constraint and complanar constraints respectively, we obtain the initial 3D structure of finger from the image by exploiting these constraints and special properties on fingers. Then by the motion properties of rigidity multi-linkage and corresponding gesture constraints, we give the general descriptions of 3D region tracking of the linkage. Finally we apply the techniques to 3D motion tracking of hand. Here genetic algorithm is employed to our optimal iteration. In order to verify the validity of our approach, we use 3D motion of fingers, which is obtained from the real image sequence, to drive our virtual model of fingers. The results demonstrate the validity of the method.